Attractive Chaos

Did you program segfault before training, or segfault during training?

No. ONNX is based on protobuf, which alone is many times larger than KANN. Supporting ONNX would defeat the goal of this project.

Parsing protobuf requires a protobuf-c, which is about the same size as kann. You additionally need translation code. With ONNX, kann won't be lightweight any more. ONNX support should be...

Thanks for your interest. I have added licensing info to k8.cc. It should be noted that k8 only works with a very old version of v8. I have archived the...

Thank you. It was renamed to `kann_layer_dense()` at some point. I have updated README.

I am thinking about CUDA. Perhaps simply replacing sgemm with cublas and convolution with cudnn alone could already give a significant boost to performance. However, I can't promise when I...

Thank you all. I am not familiar with CUDA. I heard with CUDA, moving data between CPU and GPU can be costly. I wonder how much speedup CUDA will deliver....

Wow, OpenBLAS is 71 times faster than kann's implementation. Several years ago, it was only twice as fast on my even older machine. I need to revisit matrix multiplication on...

KANN doesn't support unpooling and deconvolution. Implementing unpooling may be easy, but implementing deconvolution efficiently is not trivial. I am occupied recently. I can fix confirmed bugs, but won't have...

Should be.